如何使用 libtorch 实现 AlexNet 网络？

最新推荐文章于 2024-05-01 11:30:00 发布

weixin_30648587

最新推荐文章于 2024-05-01 11:30:00 发布

阅读量155

点赞数 1

CC 4.0 BY-SA版权

文章标签：人工智能

原文链接：http://www.cnblogs.com/cheungxiongwei/p/10711923.html

本文详细介绍了如何使用PyTorch的C++前端LibTorch实现经典的AlexNet网络。从定义模块开始，逐步构建包括卷积层、全连接层在内的网络结构，并实现了前向传播算法。适用于希望在C++环境中利用深度学习模型的开发者。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

如何使用 libtorch 实现 AlexNet 网络？

1*mgYrpXPI1aOLyVtIeQYfAw.png

按照图片上流程写即可。输入的图片大小必须 227x227 3 通道彩色图片

// Define a new Module.
struct Net : torch::nn::Module {
    Net() {
        conv1 = torch::nn::Conv2d(torch::nn::Conv2dOptions(3, 96, { 11,11 }).stride({4,4}));
        conv2 = torch::nn::Conv2d(torch::nn::Conv2dOptions(96, 256, { 5,5 }).padding(2));
        conv3 = torch::nn::Conv2d(torch::nn::Conv2dOptions(256, 384, { 3,3 }).padding(1));
        conv4 = torch::nn::Conv2d(torch::nn::Conv2dOptions(384, 384, { 3,3 }).padding(1));
        conv5 = torch::nn::Conv2d(torch::nn::Conv2dOptions(384, 256, { 3,3 }).padding(1));

        fc1 = torch::nn::Linear(256*6*6,4096);
        fc2 = torch::nn::Linear(4096, 4096);
        fc3 = torch::nn::Linear(4096, 1000);
    }

    // Implement the Net's algorithm.
    torch::Tensor forward(torch::Tensor x) {

        x = conv1->forward(x);
        x = torch::relu(x);
        //LRN
        x = torch::max_pool2d(x, { 3,3 }, { 2,2 });
        x = conv2->forward(x);
        //LRN
        x = torch::relu(x);
        x = torch::max_pool2d(x, { 3,3 }, { 2,2 });
        x = conv3->forward(x);
        x = torch::relu(x);
        x = conv4->forward(x);
        x = torch::relu(x);
        x = conv5->forward(x);
        x = torch::relu(x);
        x = torch::max_pool2d(x, { 3,3 }, { 2,2 });

        x = x.view({ x.size(0),-1 });
        x = fc1->forward(x);
        x = torch::relu(x);
        x = torch::dropout(x,0.5,is_training());

        x = fc2->forward(x);
        x = torch::relu(x);
        x = torch::dropout(x, 0.5, is_training());

        x = fc3->forward(x);

        x = torch::log_softmax(x,1);
        return x;
    }

    // Use one of many "standard library" modules.
    torch::nn::Conv2d conv1{ nullptr };
    torch::nn::Conv2d conv2{ nullptr };
    torch::nn::Conv2d conv3{ nullptr };
    torch::nn::Conv2d conv4{ nullptr };
    torch::nn::Conv2d conv5{ nullptr };
    torch::nn::Linear fc1{ nullptr };
    torch::nn::Linear fc2{ nullptr };
    torch::nn::Linear fc3{ nullptr };
};

具体可参考这个

name: "AlexNet"
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 10 dim: 3 dim: 227 dim: 227 } }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 11
    stride: 4
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "norm1"
  type: "LRN"
  bottom: "conv1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "norm1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    group: 2
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "norm2"
  type: "LRN"
  bottom: "conv2"
  top: "norm2"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "norm2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 2
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    group: 2
  }
}
layer {
  name: "relu5"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "pool5"
  type: "Pooling"
  bottom: "conv5"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "pool5"
  top: "fc6"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 4096
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}
layer {
  name: "drop6"
  type: "Dropout"
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 4096
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}
layer {
  name: "drop7"
  type: "Dropout"
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc8"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1000
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "fc8"
  top: "prob"
}

转载于:https://www.cnblogs.com/cheungxiongwei/p/10711923.html